All-in-one Python AI framework for semantic search, RAG, LLM orchestration and language model workflows, built on an embeddings database.
13.1K+37 this week972PythonApache-2.0Well maintainedUpdated yesterday
milvus-io/bootcamp
A collection of Jupyter notebook tutorials and demos showing how to build unstructured-data search and AI applications with the Milvus vector database.
- Stars
- 2,451
- Forks
- 684
- Open issues
- 0
- Last commit
- 18 days ago
What is it?
This repository is a set of hands-on notebooks and demo projects for Milvus, an open-source vector database. It covers searching unstructured data such as images, audio, text, video and molecular structures by similarity, along with question answering and NLP scenarios.
The tutorials walk through common patterns including retrieval-augmented generation (RAG), semantic search, hybrid search combining dense and sparse embeddings, full text search, and recommendation systems. Several examples show how Milvus integrates with frameworks such as LangChain and LlamaIndex.
The content is organized as runnable notebooks, so developers can follow each example step by step and adapt the code to their own data.
Key features
- 01Notebook tutorials for RAG, semantic search and hybrid search with Milvus
- 02Examples for image, audio and molecular similarity search
- 03Integration examples with LangChain and LlamaIndex
- 04Demos of full text search and multi-vector search
- 05Recommendation system and clustering examples
Use cases
- Learning how to build a retrieval-augmented generation pipeline on a vector database
- Prototyping image or audio similarity search for a product
- Exploring hybrid search that mixes dense and sparse embeddings
- Using the notebooks as a starting template for a Milvus-based demo
In collections
Topics
FAQ
- What is bootcamp?
- A collection of Jupyter notebook tutorials and demos showing how to build unstructured-data search and AI applications with the Milvus vector database. This repository is a set of hands-on notebooks and demo projects for Milvus, an open-source vector database. It covers searching unstructured data such as images, audio, text, video and molecular structures by similarity, along with question answering and NLP scenarios.
- Is bootcamp free to use? What license does it have?
- bootcamp is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is bootcamp still maintained?
- Actively maintained. The last commit to bootcamp was on Oct 21, 2026.
- What can I use bootcamp for?
- Learning how to build a retrieval-augmented generation pipeline on a vector database Prototyping image or audio similarity search for a product Exploring hybrid search that mixes dense and sparse embeddings Using the notebooks as a starting template for a Milvus-based demo
- Where can I get bootcamp?
- The source code and installation instructions are on GitHub: https://github.com/milvus-io/bootcamp
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A retrieval toolkit from BAAI providing BGE embedding and reranker models plus training, evaluation and tutorials for search and RAG.
12.3K+13 this week947PythonMITUpdated 12 days ago
Open-source embedding database for AI apps, storing documents and vectors to power semantic, hybrid and full-text search.
29.7K+36 this week2.6KRustApache-2.0Updated 18 hours ago
Epsilla is an open-source C++ vector database for embedding similarity search, with metadata filtering, hybrid search, and LLM retrieval integrations.
87446C++Apache-2.0Updated last month
Official TypeScript/Node.js SDK for Pinecone, a managed vector and full-text search database.
27950TypeScriptApache-2.0Well maintainedUpdated 2 days ago
A lightweight Python chunking library that splits text into chunks for RAG pipelines, with multiple chunkers, refiners and vector database integrations.
4.8K+8 this week370PythonMITUpdated 2 days ago